{"id":"https://openalex.org/W3160359712","doi":"https://doi.org/10.1109/icassp39728.2021.9413661","title":"Detecting Adversarial Attacks on Audiovisual Speech Recognition","display_name":"Detecting Adversarial Attacks on Audiovisual Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3160359712","doi":"https://doi.org/10.1109/icassp39728.2021.9413661","mag":"3160359712"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9413661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001790767","display_name":"Pingchuan Ma","orcid":"https://orcid.org/0000-0003-3752-0803"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Pingchuan Ma","raw_affiliation_strings":["Imperial College,Department of Computing,London,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College,Department of Computing,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475700","display_name":"Stavros Petridis","orcid":"https://orcid.org/0000-0001-7478-9479"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stavros Petridis","raw_affiliation_strings":["Imperial College,Department of Computing,London,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College,Department of Computing,London,UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016033078","display_name":"Maja Panti\u0107","orcid":"https://orcid.org/0000-0002-3620-5986"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Maja Pantic","raw_affiliation_strings":["Imperial College,Department of Computing,London,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College,Department of Computing,London,UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001790767"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":1.2238,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.82952505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6403","last_page":"6407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9721999764442444,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.921486496925354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8237097859382629},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5751129388809204},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5441374182701111},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.4513890743255615},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4433843493461609},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.42049455642700195},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17009979486465454}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.921486496925354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237097859382629},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5751129388809204},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5441374182701111},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4513890743255615},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4433843493461609},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.42049455642700195},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17009979486465454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9413661","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9413661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2015143272","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2607219512","https://openalex.org/W2736899637","https://openalex.org/W2765424254","https://openalex.org/W2782403400","https://openalex.org/W2892852825","https://openalex.org/W2950864153","https://openalex.org/W2963070423","https://openalex.org/W2963207607","https://openalex.org/W2963528589","https://openalex.org/W2963542245","https://openalex.org/W2963557656","https://openalex.org/W2964082701","https://openalex.org/W2964095416","https://openalex.org/W2964153729","https://openalex.org/W2964301649","https://openalex.org/W2964311653","https://openalex.org/W2972504708","https://openalex.org/W3103557498","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6719080892","https://openalex.org/W6734491695","https://openalex.org/W6735927292","https://openalex.org/W6736207377","https://openalex.org/W6741036071","https://openalex.org/W6746608116","https://openalex.org/W6746882984","https://openalex.org/W6751750676","https://openalex.org/W6754602573"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4366150264","https://openalex.org/W2368066043","https://openalex.org/W4306674287","https://openalex.org/W4367722749","https://openalex.org/W3024390022","https://openalex.org/W4224009465","https://openalex.org/W2903917280","https://openalex.org/W4286629047","https://openalex.org/W4304891817"],"abstract_inverted_index":{"Adversarial":[0],"attacks":[1,105,115],"pose":[2],"a":[3,76],"threat":[4],"to":[5,65],"deep":[6],"learning":[7],"models.":[8,110],"However,":[9],"research":[10],"on":[11,35,83,101,106,116,123],"adversarial":[12,56,67,88,104,114],"detection":[13,32,102],"methods,":[14],"especially":[15],"in":[16,55],"the":[17,36,49,71,91,98,124,134],"multi-modal":[18],"domain,":[19],"is":[20,47,97,137],"very":[21],"limited.":[22],"In":[23],"this":[24,96],"work,":[25],"we":[26,85],"propose":[27],"an":[28,138],"efficient":[29],"and":[30,41,53,81,126],"straightforward":[31],"method":[33],"based":[34,82],"temporal":[37],"correlation":[38,50,80],"between":[39,51],"audio":[40,52],"video":[42,54],"streams.":[43],"The":[44,129],"main":[45],"idea":[46],"that":[48,133],"examples":[57,63],"will":[58],"be":[59],"lower":[60],"than":[61],"benign":[62],"due":[64],"added":[66],"noise.":[68],"We":[69,111],"use":[70],"synchronisation":[72],"confidence":[73],"score":[74],"as":[75],"proxy":[77],"for":[78,141],"audiovisual":[79,107,118],"it":[84],"can":[86],"detect":[87],"attacks.":[89,144],"To":[90],"best":[92],"of":[93,103],"our":[94],"knowledge,":[95],"first":[99],"work":[100],"speech":[108,119],"recognition":[109,120],"apply":[112],"recent":[113],"two":[117],"models":[121],"trained":[122],"GRID":[125],"LRW":[127],"datasets.":[128],"experimental":[130],"results":[131],"demonstrate":[132],"proposed":[135],"approach":[136],"effective":[139],"way":[140],"detecting":[142],"such":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3}],"updated_date":"2026-02-22T13:39:03.778224","created_date":"2025-10-10T00:00:00"}